So, how to achieve global optimal codebook become the one of key problems of designing VQ algorithm.
因此,如何获得全局最优的码书成为矢量量化算法设计的主要研究问题之一。
The experiment of using different phonetic parameter indicates that the VQ algorithm is an effective method in speaker recognition.
用不同语音参数进行实验,实验表明应用矢量量化的方法用在说话人识别中是一种有效方法。
VQ Model Based on Clustering Validity Analysis: it's the flaw for the codebook training algorithm that the size of codebook is choosed artificially.
基于聚类有效性分析的VQ模型:VQ模型电码本的训练算法有一个弱点:电码本大小是人为指定的。
应用推荐